代碼地址：https://code.csdn.net/ranky2009/pythonsmallproject
編碼中遇到的問題Note：
1.在編寫中發現使用newnews時出現如下錯誤：
502 NEWNEWS command disabled by administrator
由於使用newnews命令出現問題，所以改爲使用其他的命令替代。用group 和article命令，見項目代碼。
2.使用如下code打印中文會報錯誤
代碼url_test.py：
from urllib.request import urlopen
with urlopen('http://www.baidu.com') as f:
print(f.read().decode('utf-8'))
錯誤：
UnicodeEncodeError: 'gbk' codec can't encode character '\ufeff' in position 0: i
llegal multibyte sequence
錯誤環境是OS：WIN7， version of python：3.4.3，窗口：控制檯cmd
後來發現，這個錯誤是由於在控制檯中運行(python url_test.py)代碼。
解決方法：
開始->所有程序->啓動IDLE (Python 3.4 GUI - 64 bit)->File->New File，將以上代碼拷貝到新文件中，F5運行代碼，發現能正確讀取中文。
注意：對於不同的網頁，要看網頁源碼是怎樣編碼方式，有的是utf-8，有的是gb2312。
3.關於match
Match必須從正則表達式開始匹配，
import re
m = re.match(‘.end’, ‘1end’)
print(m.group()) #能夠匹配到1end
n = re.match(‘.end, ‘12end’)
print(n.group()) #n爲None，報錯
對書上原始代碼略做修改，如下：
from nntplib import NNTP
from time import strftime, time, localtime
from email import message_from_string
from urllib.request import urlopen
import textwrap
import re
def wrap(string, max = 70):
return '\n'.join(textwrap.wrap(string)) + '\n'
class NewsAgent:
def __init__(self):
self.sources = []
self.destinations = []
def addSource(self, source):
self.sources.append(source)
def addDestination(self, dest):
self.destinations.append(dest)
def distribute(self):
items = []
for source in self.sources:
items.extend(source.getItems())
for dest in self.destinations:
dest.receiveItems(items)
class NewsItem:
def __init__(self, title, body):
self.title = title
self.body = body
class NNTPSource:
def __init__(self, servername, group, window):
self.servername = servername
self.group = group
self.window = window
def getItems(self):
server = NNTP(self.servername)
groupInfo = server.group(self.group)
for num in range(5):
id = str(int(groupInfo[2]) + num)
articleinfo = server.article(id)[1]
articleinfoStrings = []
for line in articleinfo.lines:
articleinfoStrings.append(line.decode())
message = message_from_string('\n'.join(articleinfoStrings))
title = message['subject']
body = message.get_payload()
if message.is_multipart():
body = body[0]
yield NewsItem(title, body)
server.quit()
class SimpleWebSource:
def __init__(self, url, titlePattern, bodyPattern):
self.url = url
self.titlePattern = re.compile(titlePattern)
self.bodyPattern = re.compile(bodyPattern)
def getItems(self):
text = urlopen(self.url).read()
textString = text.decode('utf-8')
title = self.titlePattern.findall(textString)
print(title)
body = self.bodyPattern.findall(textString)
#print(body[0])
for line in body:
if len(line) > 30 :
yield NewsItem(title[0], wrap(line))
break
class PlainDestination:
def receiveItems(self, items):
for item in items:
print(item.title)
print('-' * len(item.title))
print(item.body)
class HTMLDestination:
def __init__(self, filename):
self.filename = filename
def receiveItems(self, items):
out = open(self.filename, 'w', encoding='utf-8')
print("""
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
<title>Today's New</title>
</head>
<body>
<h1>Today's News</h1>
""", file = out)
print('<ul>', file = out)
id = 0
for item in items:
id += 1
print('<li><a href="#%i">%s</a></li>' % (id, item.title), file = out)
print('</ul', file = out)
id = 0
for item in items:
id += 1
print('<h2><a name="%i">%s</a></h2>' % (id, item.title), file = out)
print('<pre>%s</pre>' % item.body, file = out)
print("""
</body>
</html>
""", file = out)
def runDefaultSetup():
agent = NewsAgent()
bbc_url = 'http://m.cnr.cn/news/20150706/t20150706_519082828_tt.html?tt_group_id=4658836325'
bbc_title = '<title>(.+?)</title>'
bbc_body = '<p.*>(.+?)</p>'
bbc = SimpleWebSource(bbc_url, bbc_title, bbc_body)
agent.addSource(bbc)
clpa_server = 'nntpswitch.blueworldhosting.com'
clpa_group = 'comp.lang.python.announce'
clpa_window = 1
clpa = NNTPSource(clpa_server, clpa_group, clpa_window)
agent.addSource(clpa)
agent.addDestination(PlainDestination())
agent.addDestination(HTMLDestination('news.html'))
agent.distribute()
if __name__ == '__main__' : runDefaultSetup()